Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/solid-company/solid-jobs-skills/claude-mdgit clone --depth 1 https://github.com/solid-company/solid-jobs-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/solid-company/solid-jobs-skills/claude-md)<a href="https://agentmods.dev/instructions/solid-company/solid-jobs-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/solid-company/solid-jobs-skills/claude-md.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.02411 | $0.02411 |
| Opus 5 | $0.01205 | $0.01205 |
| Sonnet 5 | $0.00482 | $0.00482 |
| Haiku 4.5 | $0.00241 | $0.00241 |
Grade A, and why
solid-jobs-skills CLAUDE.md scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`~/.solid-jobs-skills/bin`. Idempotent (skips if version matches). Skills curl How it starts
The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
solid-jobs-skills
An AI job-search command center for the SOLID.Jobs public API.
A Go binary (sjctl) does the deterministic work — fetching offers, caching, tracking, stats —
and Claude skills add the judgment layer (search-from-language, offer evaluation,
digests).
Architecture
cmd/sjctl CLI (cobra) — thin wrapper, no business logic
internal/api SOLID.Jobs API client (typed models, campaign param, 429 backoff)
internal/store SQLite store — typed wrappers over the generated queries
internal/store/schema.sql table definitions (sqlc source + runtime DDL)
internal/store/query.sql all SQL queries (sqlc source)
internal/store/sqlcgen GENERATED by sqlc — do not edit by hand
internal/jobs Service layer — ALL business logic lives here
internal/stats Salary/market aggregation
.claude/skills jobs-search, jobs-create-profile, jobs-evaluate, jobs-track, jobs-digest, jobs-interview, jobs-market
config/ profile.md template
data/ solidjobs.db (gitignored)
Dependency rule: cmd/sjctl and any future dashboard depend on internal/jobs,
never the reverse. Put logic in the service layer, not in commands. SQLite is the
single source of truth for offers, profiles, tracker, evaluations, interview
preps and watches.
SQL rule: no SQL is inlined in Go. All queries live in internal/store/query.sql
and the schema in internal/store/schema.sql; sqlc compiles them
into the typed sqlcgen package. The store package wraps those generated methods.
To change the database layer: edit the .sql files, run sqlc generate, then update
the wrappers in internal/store/*.go.
Build & run
sqlc generate # regenerate internal/store/sqlcgen after editing *.sql
go build -o sjctl ./cmd/sjctl # build the binary (sjctl.exe on Windows)
go test ./... # run tests
./sjctl search -d IT --term golang --remote --json
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 159 lines · 2,411 tokens per session scan A 718c8c96b89d
solid-jobs-skills CLAUDE.md is an instructions file published in the GitHub repository solid-company/solid-jobs-skills (5 stars, last pushed 23d ago), licensed MIT. It adds 2,411 tokens to every session, about $0.0121 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).